Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next

Pull networking updates from David Miller:

 1) Add Maglev hashing scheduler to IPVS, from Inju Song.

 2) Lots of new TC subsystem tests from Roman Mashak.

 3) Add TCP zero copy receive and fix delayed acks and autotuning with
    SO_RCVLOWAT, from Eric Dumazet.

 4) Add XDP_REDIRECT support to mlx5 driver, from Jesper Dangaard
    Brouer.

 5) Add ttl inherit support to vxlan, from Hangbin Liu.

 6) Properly separate ipv6 routes into their logically independant
    components. fib6_info for the routing table, and fib6_nh for sets of
    nexthops, which thus can be shared. From David Ahern.

 7) Add bpf_xdp_adjust_tail helper, which can be used to generate ICMP
    messages from XDP programs. From Nikita V. Shirokov.

 8) Lots of long overdue cleanups to the r8169 driver, from Heiner
    Kallweit.

 9) Add BTF ("BPF Type Format"), from Martin KaFai Lau.

10) Add traffic condition monitoring to iwlwifi, from Luca Coelho.

11) Plumb extack down into fib_rules, from Roopa Prabhu.

12) Add Flower classifier offload support to igb, from Vinicius Costa
    Gomes.

13) Add UDP GSO support, from Willem de Bruijn.

14) Add documentation for eBPF helpers, from Quentin Monnet.

15) Add TLS tx offload to mlx5, from Ilya Lesokhin.

16) Allow applications to be given the number of bytes available to read
    on a socket via a control message returned from recvmsg(), from
    Soheil Hassas Yeganeh.

17) Add x86_32 eBPF JIT compiler, from Wang YanQing.

18) Add AF_XDP sockets, with zerocopy support infrastructure as well.
    From Björn Töpel.

19) Remove indirect load support from all of the BPF JITs and handle
    these operations in the verifier by translating them into native BPF
    instead. From Daniel Borkmann.

20) Add GRO support to ipv6 gre tunnels, from Eran Ben Elisha.

21) Allow XDP programs to do lookups in the main kernel routing tables
    for forwarding. From David Ahern.

22) Allow drivers to store hardware state into an ELF section of kernel
    dump vmcore files, and use it in cxgb4. From Rahul Lakkireddy.

23) Various RACK and loss detection improvements in TCP, from Yuchung
    Cheng.

24) Add TCP SACK compression, from Eric Dumazet.

25) Add User Mode Helper support and basic bpfilter infrastructure, from
    Alexei Starovoitov.

26) Support ports and protocol values in RTM_GETROUTE, from Roopa
    Prabhu.

27) Support bulking in ->ndo_xdp_xmit() API, from Jesper Dangaard
    Brouer.

28) Add lots of forwarding selftests, from Petr Machata.

29) Add generic network device failover driver, from Sridhar Samudrala.

* ra.kernel.org:/pub/scm/linux/kernel/git/davem/net-next: (1959 commits)
  strparser: Add __strp_unpause and use it in ktls.
  rxrpc: Fix terminal retransmission connection ID to include the channel
  net: hns3: Optimize PF CMDQ interrupt switching process
  net: hns3: Fix for VF mailbox receiving unknown message
  net: hns3: Fix for VF mailbox cannot receiving PF response
  bnx2x: use the right constant
  Revert "net: sched: cls: Fix offloading when ingress dev is vxlan"
  net: dsa: b53: Fix for brcm tag issue in Cygnus SoC
  enic: fix UDP rss bits
  netdev-FAQ: clarify DaveM's position for stable backports
  rtnetlink: validate attributes in do_setlink()
  mlxsw: Add extack messages for port_{un, }split failures
  netdevsim: Add extack error message for devlink reload
  devlink: Add extack to reload and port_{un, }split operations
  net: metrics: add proper netlink validation
  ipmr: fix error path when ipmr_new_table fails
  ip6mr: only set ip6mr_table from setsockopt when ip6mr_new_table succeeds
  net: hns3: remove unused hclgevf_cfg_func_mta_filter
  netfilter: provide udp*_lib_lookup for nf_tproxy
  qed*: Utilize FW 8.37.2.0
  ...

1 files changed, 184 insertions, 87 deletions

diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index e51c644484dc..355d3dffd021 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -111,6 +111,25 @@ int sysctl_tcp_max_orphans __read_mostly = NR_FILE;
 #define REXMIT_LOST	1 /* retransmit packets marked lost */
 #define REXMIT_NEW	2 /* FRTO-style transmit of unsent/new packets */
 
+#if IS_ENABLED(CONFIG_TLS_DEVICE)
+static DEFINE_STATIC_KEY_FALSE(clean_acked_data_enabled);
+
+void clean_acked_data_enable(struct inet_connection_sock *icsk,
+			     void (*cad)(struct sock *sk, u32 ack_seq))
+{
+	icsk->icsk_clean_acked = cad;
+	static_branch_inc(&clean_acked_data_enabled);
+}
+EXPORT_SYMBOL_GPL(clean_acked_data_enable);
+
+void clean_acked_data_disable(struct inet_connection_sock *icsk)
+{
+	static_branch_dec(&clean_acked_data_enabled);
+	icsk->icsk_clean_acked = NULL;
+}
+EXPORT_SYMBOL_GPL(clean_acked_data_disable);
+#endif
+
 static void tcp_gro_dev_warn(struct sock *sk, const struct sk_buff *skb,
 			     unsigned int len)
 {
@@ -184,21 +203,23 @@ static void tcp_measure_rcv_mss(struct sock *sk, const struct sk_buff *skb)
 	}
 }
 
-static void tcp_incr_quickack(struct sock *sk)
+static void tcp_incr_quickack(struct sock *sk, unsigned int max_quickacks)
 {
 	struct inet_connection_sock *icsk = inet_csk(sk);
 	unsigned int quickacks = tcp_sk(sk)->rcv_wnd / (2 * icsk->icsk_ack.rcv_mss);
 
 	if (quickacks == 0)
 		quickacks = 2;
+	quickacks = min(quickacks, max_quickacks);
 	if (quickacks > icsk->icsk_ack.quick)
-		icsk->icsk_ack.quick = min(quickacks, TCP_MAX_QUICKACKS);
+		icsk->icsk_ack.quick = quickacks;
 }
 
-static void tcp_enter_quickack_mode(struct sock *sk)
+static void tcp_enter_quickack_mode(struct sock *sk, unsigned int max_quickacks)
 {
 	struct inet_connection_sock *icsk = inet_csk(sk);
-	tcp_incr_quickack(sk);
+
+	tcp_incr_quickack(sk, max_quickacks);
 	icsk->icsk_ack.pingpong = 0;
 	icsk->icsk_ack.ato = TCP_ATO_MIN;
 }
@@ -233,8 +254,10 @@ static void tcp_ecn_withdraw_cwr(struct tcp_sock *tp)
 	tp->ecn_flags &= ~TCP_ECN_DEMAND_CWR;
 }
 
-static void __tcp_ecn_check_ce(struct tcp_sock *tp, const struct sk_buff *skb)
+static void __tcp_ecn_check_ce(struct sock *sk, const struct sk_buff *skb)
 {
+	struct tcp_sock *tp = tcp_sk(sk);
+
 	switch (TCP_SKB_CB(skb)->ip_dsfield & INET_ECN_MASK) {
 	case INET_ECN_NOT_ECT:
 		/* Funny extension: if ECT is not set on a segment,
@@ -242,31 +265,31 @@ static void __tcp_ecn_check_ce(struct tcp_sock *tp, const struct sk_buff *skb)
 		 * it is probably a retransmit.
 		 */
 		if (tp->ecn_flags & TCP_ECN_SEEN)
-			tcp_enter_quickack_mode((struct sock *)tp);
+			tcp_enter_quickack_mode(sk, 1);
 		break;
 	case INET_ECN_CE:
-		if (tcp_ca_needs_ecn((struct sock *)tp))
-			tcp_ca_event((struct sock *)tp, CA_EVENT_ECN_IS_CE);
+		if (tcp_ca_needs_ecn(sk))
+			tcp_ca_event(sk, CA_EVENT_ECN_IS_CE);
 
 		if (!(tp->ecn_flags & TCP_ECN_DEMAND_CWR)) {
 			/* Better not delay acks, sender can have a very low cwnd */
-			tcp_enter_quickack_mode((struct sock *)tp);
+			tcp_enter_quickack_mode(sk, 1);
 			tp->ecn_flags |= TCP_ECN_DEMAND_CWR;
 		}
 		tp->ecn_flags |= TCP_ECN_SEEN;
 		break;
 	default:
-		if (tcp_ca_needs_ecn((struct sock *)tp))
-			tcp_ca_event((struct sock *)tp, CA_EVENT_ECN_NO_CE);
+		if (tcp_ca_needs_ecn(sk))
+			tcp_ca_event(sk, CA_EVENT_ECN_NO_CE);
 		tp->ecn_flags |= TCP_ECN_SEEN;
 		break;
 	}
 }
 
-static void tcp_ecn_check_ce(struct tcp_sock *tp, const struct sk_buff *skb)
+static void tcp_ecn_check_ce(struct sock *sk, const struct sk_buff *skb)
 {
-	if (tp->ecn_flags & TCP_ECN_OK)
-		__tcp_ecn_check_ce(tp, skb);
+	if (tcp_sk(sk)->ecn_flags & TCP_ECN_OK)
+		__tcp_ecn_check_ce(sk, skb);
 }
 
 static void tcp_ecn_rcv_synack(struct tcp_sock *tp, const struct tcphdr *th)
@@ -582,6 +605,8 @@ void tcp_rcv_space_adjust(struct sock *sk)
 	u32 copied;
 	int time;
 
+	trace_tcp_rcv_space_adjust(sk);
+
 	tcp_mstamp_refresh(tp);
 	time = tcp_stamp_us_delta(tp->tcp_mstamp, tp->rcvq_space.time);
 	if (time < (tp->rcv_rtt_est.rtt_us >> 3) || tp->rcv_rtt_est.rtt_us == 0)
@@ -665,7 +690,7 @@ static void tcp_event_data_recv(struct sock *sk, struct sk_buff *skb)
 		/* The _first_ data packet received, initialize
 		 * delayed ACK engine.
 		 */
-		tcp_incr_quickack(sk);
+		tcp_incr_quickack(sk, TCP_MAX_QUICKACKS);
 		icsk->icsk_ack.ato = TCP_ATO_MIN;
 	} else {
 		int m = now - icsk->icsk_ack.lrcvtime;
@@ -681,13 +706,13 @@ static void tcp_event_data_recv(struct sock *sk, struct sk_buff *skb)
 			/* Too long gap. Apparently sender failed to
 			 * restart window, so that we send ACKs quickly.
 			 */
-			tcp_incr_quickack(sk);
+			tcp_incr_quickack(sk, TCP_MAX_QUICKACKS);
 			sk_mem_reclaim(sk);
 		}
 	}
 	icsk->icsk_ack.lrcvtime = now;
 
-	tcp_ecn_check_ce(tp, skb);
+	tcp_ecn_check_ce(sk, skb);
 
 	if (skb->len >= 128)
 		tcp_grow_window(sk, skb);
@@ -1896,19 +1921,54 @@ static inline void tcp_init_undo(struct tcp_sock *tp)
 	tp->undo_retrans = tp->retrans_out ? : -1;
 }
 
-/* Enter Loss state. If we detect SACK reneging, forget all SACK information
+static bool tcp_is_rack(const struct sock *sk)
+{
+	return sock_net(sk)->ipv4.sysctl_tcp_recovery & TCP_RACK_LOSS_DETECTION;
+}
+
+/* If we detect SACK reneging, forget all SACK information
  * and reset tags completely, otherwise preserve SACKs. If receiver
  * dropped its ofo queue, we will know this due to reneging detection.
  */
+static void tcp_timeout_mark_lost(struct sock *sk)
+{
+	struct tcp_sock *tp = tcp_sk(sk);
+	struct sk_buff *skb, *head;
+	bool is_reneg;			/* is receiver reneging on SACKs? */
+
+	head = tcp_rtx_queue_head(sk);
+	is_reneg = head && (TCP_SKB_CB(head)->sacked & TCPCB_SACKED_ACKED);
+	if (is_reneg) {
+		NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPSACKRENEGING);
+		tp->sacked_out = 0;
+		/* Mark SACK reneging until we recover from this loss event. */
+		tp->is_sack_reneg = 1;
+	} else if (tcp_is_reno(tp)) {
+		tcp_reset_reno_sack(tp);
+	}
+
+	skb = head;
+	skb_rbtree_walk_from(skb) {
+		if (is_reneg)
+			TCP_SKB_CB(skb)->sacked &= ~TCPCB_SACKED_ACKED;
+		else if (tcp_is_rack(sk) && skb != head &&
+			 tcp_rack_skb_timeout(tp, skb, 0) > 0)
+			continue; /* Don't mark recently sent ones lost yet */
+		tcp_mark_skb_lost(sk, skb);
+	}
+	tcp_verify_left_out(tp);
+	tcp_clear_all_retrans_hints(tp);
+}
+
+/* Enter Loss state. */
 void tcp_enter_loss(struct sock *sk)
 {
 	const struct inet_connection_sock *icsk = inet_csk(sk);
 	struct tcp_sock *tp = tcp_sk(sk);
 	struct net *net = sock_net(sk);
-	struct sk_buff *skb;
 	bool new_recovery = icsk->icsk_ca_state < TCP_CA_Recovery;
-	bool is_reneg;			/* is receiver reneging on SACKs? */
-	bool mark_lost;
+
+	tcp_timeout_mark_lost(sk);
 
 	/* Reduce ssthresh if it has not yet been made inside this window. */
 	if (icsk->icsk_ca_state <= TCP_CA_Disorder ||
@@ -1920,40 +1980,10 @@ void tcp_enter_loss(struct sock *sk)
 		tcp_ca_event(sk, CA_EVENT_LOSS);
 		tcp_init_undo(tp);
 	}
-	tp->snd_cwnd	   = 1;
+	tp->snd_cwnd	   = tcp_packets_in_flight(tp) + 1;
 	tp->snd_cwnd_cnt   = 0;
 	tp->snd_cwnd_stamp = tcp_jiffies32;
 
-	tp->retrans_out = 0;
-	tp->lost_out = 0;
-
-	if (tcp_is_reno(tp))
-		tcp_reset_reno_sack(tp);
-
-	skb = tcp_rtx_queue_head(sk);
-	is_reneg = skb && (TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_ACKED);
-	if (is_reneg) {
-		NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPSACKRENEGING);
-		tp->sacked_out = 0;
-		/* Mark SACK reneging until we recover from this loss event. */
-		tp->is_sack_reneg = 1;
-	}
-	tcp_clear_all_retrans_hints(tp);
-
-	skb_rbtree_walk_from(skb) {
-		mark_lost = (!(TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_ACKED) ||
-			     is_reneg);
-		if (mark_lost)
-			tcp_sum_lost(tp, skb);
-		TCP_SKB_CB(skb)->sacked &= (~TCPCB_TAGBITS)|TCPCB_SACKED_ACKED;
-		if (mark_lost) {
-			TCP_SKB_CB(skb)->sacked &= ~TCPCB_SACKED_ACKED;
-			TCP_SKB_CB(skb)->sacked |= TCPCB_LOST;
-			tp->lost_out += tcp_skb_pcount(skb);
-		}
-	}
-	tcp_verify_left_out(tp);
-
 	/* Timeout in disordered state after receiving substantial DUPACKs
 	 * suggests that the degree of reordering is over-estimated.
 	 */
@@ -2120,7 +2150,7 @@ static bool tcp_time_to_recover(struct sock *sk, int flag)
 		return true;
 
 	/* Not-A-Trick#2 : Classic rule... */
-	if (tcp_dupack_heuristics(tp) > tp->reordering)
+	if (!tcp_is_rack(sk) && tcp_dupack_heuristics(tp) > tp->reordering)
 		return true;
 
 	return false;
@@ -2197,9 +2227,7 @@ static void tcp_update_scoreboard(struct sock *sk, int fast_rexmit)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
 
-	if (tcp_is_reno(tp)) {
-		tcp_mark_head_lost(sk, 1, 1);
-	} else {
+	if (tcp_is_sack(tp)) {
 		int sacked_upto = tp->sacked_out - tp->reordering;
 		if (sacked_upto >= 0)
 			tcp_mark_head_lost(sk, sacked_upto, 0);
@@ -2697,12 +2725,16 @@ static bool tcp_try_undo_partial(struct sock *sk, u32 prior_snd_una)
 	return false;
 }
 
-static void tcp_rack_identify_loss(struct sock *sk, int *ack_flag)
+static void tcp_identify_packet_loss(struct sock *sk, int *ack_flag)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
 
-	/* Use RACK to detect loss */
-	if (sock_net(sk)->ipv4.sysctl_tcp_recovery & TCP_RACK_LOSS_DETECTION) {
+	if (tcp_rtx_queue_empty(sk))
+		return;
+
+	if (unlikely(tcp_is_reno(tp))) {
+		tcp_newreno_mark_lost(sk, *ack_flag & FLAG_SND_UNA_ADVANCED);
+	} else if (tcp_is_rack(sk)) {
 		u32 prior_retrans = tp->retrans_out;
 
 		tcp_rack_mark_lost(sk);
@@ -2798,11 +2830,11 @@ static void tcp_fastretrans_alert(struct sock *sk, const u32 prior_snd_una,
 			tcp_try_keep_open(sk);
 			return;
 		}
-		tcp_rack_identify_loss(sk, ack_flag);
+		tcp_identify_packet_loss(sk, ack_flag);
 		break;
 	case TCP_CA_Loss:
 		tcp_process_loss(sk, flag, is_dupack, rexmit);
-		tcp_rack_identify_loss(sk, ack_flag);
+		tcp_identify_packet_loss(sk, ack_flag);
 		if (!(icsk->icsk_ca_state == TCP_CA_Open ||
 		      (*ack_flag & FLAG_LOST_RETRANS)))
 			return;
@@ -2819,7 +2851,7 @@ static void tcp_fastretrans_alert(struct sock *sk, const u32 prior_snd_una,
 		if (icsk->icsk_ca_state <= TCP_CA_Disorder)
 			tcp_try_undo_dsack(sk);
 
-		tcp_rack_identify_loss(sk, ack_flag);
+		tcp_identify_packet_loss(sk, ack_flag);
 		if (!tcp_time_to_recover(sk, flag)) {
 			tcp_try_to_open(sk, flag);
 			return;
@@ -2841,7 +2873,7 @@ static void tcp_fastretrans_alert(struct sock *sk, const u32 prior_snd_una,
 		fast_rexmit = 1;
 	}
 
-	if (do_lost)
+	if (!tcp_is_rack(sk) && do_lost)
 		tcp_update_scoreboard(sk, fast_rexmit);
 	*rexmit = REXMIT_LOST;
 }
@@ -3496,6 +3528,22 @@ static void tcp_xmit_recovery(struct sock *sk, int rexmit)
 	tcp_xmit_retransmit_queue(sk);
 }
 
+/* Returns the number of packets newly acked or sacked by the current ACK */
+static u32 tcp_newly_delivered(struct sock *sk, u32 prior_delivered, int flag)
+{
+	const struct net *net = sock_net(sk);
+	struct tcp_sock *tp = tcp_sk(sk);
+	u32 delivered;
+
+	delivered = tp->delivered - prior_delivered;
+	NET_ADD_STATS(net, LINUX_MIB_TCPDELIVERED, delivered);
+	if (flag & FLAG_ECE) {
+		tp->delivered_ce += delivered;
+		NET_ADD_STATS(net, LINUX_MIB_TCPDELIVEREDCE, delivered);
+	}
+	return delivered;
+}
+
 /* This routine deals with incoming acks, but not outgoing ones. */
 static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag)
 {
@@ -3542,6 +3590,12 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag)
 	if (after(ack, prior_snd_una)) {
 		flag |= FLAG_SND_UNA_ADVANCED;
 		icsk->icsk_retransmits = 0;
+
+#if IS_ENABLED(CONFIG_TLS_DEVICE)
+		if (static_branch_unlikely(&clean_acked_data_enabled))
+			if (icsk->icsk_clean_acked)
+				icsk->icsk_clean_acked(sk, ack);
+#endif
 	}
 
 	prior_fack = tcp_is_sack(tp) ? tcp_highest_sack_seq(tp) : tp->snd_una;
@@ -3619,7 +3673,7 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag)
 	if ((flag & FLAG_FORWARD_PROGRESS) || !(flag & FLAG_NOT_DUP))
 		sk_dst_confirm(sk);
 
-	delivered = tp->delivered - delivered;	/* freshly ACKed or SACKed */
+	delivered = tcp_newly_delivered(sk, delivered, flag);
 	lost = tp->lost - lost;			/* freshly marked lost */
 	rs.is_ack_delayed = !!(flag & FLAG_ACK_MAYBE_DELAYED);
 	tcp_rate_gen(sk, delivered, lost, is_sack_reneg, sack_state.rate);
@@ -3629,9 +3683,11 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag)
 
 no_queue:
 	/* If data was DSACKed, see if we can undo a cwnd reduction. */
-	if (flag & FLAG_DSACKING_ACK)
+	if (flag & FLAG_DSACKING_ACK) {
 		tcp_fastretrans_alert(sk, prior_snd_una, is_dupack, &flag,
 				      &rexmit);
+		tcp_newly_delivered(sk, delivered, flag);
+	}
 	/* If this ack opens up a zero window, clear backoff.  It was
 	 * being used to time the probes, and is probably far higher than
 	 * it needs to be for normal retransmission.
@@ -3655,6 +3711,7 @@ old_ack:
 						&sack_state);
 		tcp_fastretrans_alert(sk, prior_snd_una, is_dupack, &flag,
 				      &rexmit);
+		tcp_newly_delivered(sk, delivered, flag);
 		tcp_xmit_recovery(sk, rexmit);
 	}
 
@@ -4126,7 +4183,7 @@ static void tcp_send_dupack(struct sock *sk, const struct sk_buff *skb)
 	if (TCP_SKB_CB(skb)->end_seq != TCP_SKB_CB(skb)->seq &&
 	    before(TCP_SKB_CB(skb)->seq, tp->rcv_nxt)) {
 		NET_INC_STATS(sock_net(sk), LINUX_MIB_DELAYEDACKLOST);
-		tcp_enter_quickack_mode(sk);
+		tcp_enter_quickack_mode(sk, TCP_MAX_QUICKACKS);
 
 		if (tcp_is_sack(tp) && sock_net(sk)->ipv4.sysctl_tcp_dsack) {
 			u32 end_seq = TCP_SKB_CB(skb)->end_seq;
@@ -4196,6 +4253,8 @@ static void tcp_sack_new_ofo_skb(struct sock *sk, u32 seq, u32 end_seq)
 	 * If the sack array is full, forget about the last one.
 	 */
 	if (this_sack >= TCP_NUM_SACKS) {
+		if (tp->compressed_ack)
+			tcp_send_ack(sk);
 		this_sack--;
 		tp->rx_opt.num_sacks--;
 		sp--;
@@ -4377,7 +4436,7 @@ static void tcp_data_queue_ofo(struct sock *sk, struct sk_buff *skb)
 	u32 seq, end_seq;
 	bool fragstolen;
 
-	tcp_ecn_check_ce(tp, skb);
+	tcp_ecn_check_ce(sk, skb);
 
 	if (unlikely(tcp_try_rmem_schedule(sk, skb, skb->truesize))) {
 		NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPOFODROP);
@@ -4573,6 +4632,17 @@ err:
 
 }
 
+void tcp_data_ready(struct sock *sk)
+{
+	const struct tcp_sock *tp = tcp_sk(sk);
+	int avail = tp->rcv_nxt - tp->copied_seq;
+
+	if (avail < sk->sk_rcvlowat && !sock_flag(sk, SOCK_DONE))
+		return;
+
+	sk->sk_data_ready(sk);
+}
+
 static void tcp_data_queue(struct sock *sk, struct sk_buff *skb)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
@@ -4630,7 +4700,7 @@ queue_and_out:
 		if (eaten > 0)
 			kfree_skb_partial(skb, fragstolen);
 		if (!sock_flag(sk, SOCK_DEAD))
-			sk->sk_data_ready(sk);
+			tcp_data_ready(sk);
 		return;
 	}
 
@@ -4640,7 +4710,7 @@ queue_and_out:
 		tcp_dsack_set(sk, TCP_SKB_CB(skb)->seq, TCP_SKB_CB(skb)->end_seq);
 
 out_of_window:
-		tcp_enter_quickack_mode(sk);
+		tcp_enter_quickack_mode(sk, TCP_MAX_QUICKACKS);
 		inet_csk_schedule_ack(sk);
 drop:
 		tcp_drop(sk, skb);
@@ -4651,8 +4721,6 @@ drop:
 	if (!before(TCP_SKB_CB(skb)->seq, tp->rcv_nxt + tcp_receive_window(tp)))
 		goto out_of_window;
 
-	tcp_enter_quickack_mode(sk);
-
 	if (before(TCP_SKB_CB(skb)->seq, tp->rcv_nxt)) {
 		/* Partial packet, seq < rcv_next < end_seq */
 		SOCK_DEBUG(sk, "partial packet: rcv_next %X seq %X - %X\n",
@@ -5019,23 +5087,48 @@ static inline void tcp_data_snd_check(struct sock *sk)
 static void __tcp_ack_snd_check(struct sock *sk, int ofo_possible)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
+	unsigned long rtt, delay;
 
 	    /* More than one full frame received... */
 	if (((tp->rcv_nxt - tp->rcv_wup) > inet_csk(sk)->icsk_ack.rcv_mss &&
 	     /* ... and right edge of window advances far enough.
-	      * (tcp_recvmsg() will send ACK otherwise). Or...
+	      * (tcp_recvmsg() will send ACK otherwise).
+	      * If application uses SO_RCVLOWAT, we want send ack now if
+	      * we have not received enough bytes to satisfy the condition.
 	      */
-	     __tcp_select_window(sk) >= tp->rcv_wnd) ||
+	    (tp->rcv_nxt - tp->copied_seq < sk->sk_rcvlowat ||
+	     __tcp_select_window(sk) >= tp->rcv_wnd)) ||
 	    /* We ACK each frame or... */
-	    tcp_in_quickack_mode(sk) ||
-	    /* We have out of order data. */
-	    (ofo_possible && !RB_EMPTY_ROOT(&tp->out_of_order_queue))) {
-		/* Then ack it now */
+	    tcp_in_quickack_mode(sk)) {
+send_now:
 		tcp_send_ack(sk);
-	} else {
-		/* Else, send delayed ack. */
+		return;
+	}
+
+	if (!ofo_possible || RB_EMPTY_ROOT(&tp->out_of_order_queue)) {
 		tcp_send_delayed_ack(sk);
+		return;
 	}
+
+	if (!tcp_is_sack(tp) ||
+	    tp->compressed_ack >= sock_net(sk)->ipv4.sysctl_tcp_comp_sack_nr)
+		goto send_now;
+	tp->compressed_ack++;
+
+	if (hrtimer_is_queued(&tp->compressed_ack_timer))
+		return;
+
+	/* compress ack timer : 5 % of rtt, but no more than tcp_comp_sack_delay_ns */
+
+	rtt = tp->rcv_rtt_est.rtt_us;
+	if (tp->srtt_us && tp->srtt_us < rtt)
+		rtt = tp->srtt_us;
+
+	delay = min_t(unsigned long, sock_net(sk)->ipv4.sysctl_tcp_comp_sack_delay_ns,
+		      rtt * (NSEC_PER_USEC >> 3)/20);
+	sock_hold(sk);
+	hrtimer_start(&tp->compressed_ack_timer, ns_to_ktime(delay),
+		      HRTIMER_MODE_REL_PINNED_SOFT);
 }
 
 static inline void tcp_ack_snd_check(struct sock *sk)
@@ -5299,11 +5392,11 @@ discard:
  *	the rest is checked inline. Fast processing is turned on in
  *	tcp_data_queue when everything is OK.
  */
-void tcp_rcv_established(struct sock *sk, struct sk_buff *skb,
-			 const struct tcphdr *th)
+void tcp_rcv_established(struct sock *sk, struct sk_buff *skb)
 {
-	unsigned int len = skb->len;
+	const struct tcphdr *th = (const struct tcphdr *)skb->data;
 	struct tcp_sock *tp = tcp_sk(sk);
+	unsigned int len = skb->len;
 
 	/* TCP congestion window tracking */
 	trace_tcp_probe(sk, skb);
@@ -5428,7 +5521,7 @@ void tcp_rcv_established(struct sock *sk, struct sk_buff *skb,
 no_ack:
 			if (eaten)
 				kfree_skb_partial(skb, fragstolen);
-			sk->sk_data_ready(sk);
+			tcp_data_ready(sk);
 			return;
 		}
 	}
@@ -5550,9 +5643,12 @@ static bool tcp_rcv_fastopen_synack(struct sock *sk, struct sk_buff *synack,
 		return true;
 	}
 	tp->syn_data_acked = tp->syn_data;
-	if (tp->syn_data_acked)
-		NET_INC_STATS(sock_net(sk),
-				LINUX_MIB_TCPFASTOPENACTIVE);
+	if (tp->syn_data_acked) {
+		NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPFASTOPENACTIVE);
+		/* SYN-data is counted as two separate packets in tcp_ack() */
+		if (tp->delivered > 1)
+			--tp->delivered;
+	}
 
 	tcp_fastopen_add_skb(sk, synack);
 
@@ -5698,7 +5794,7 @@ static int tcp_rcv_synsent_state_process(struct sock *sk, struct sk_buff *skb,
 			 * to stand against the temptation 8)     --ANK
 			 */
 			inet_csk_schedule_ack(sk);
-			tcp_enter_quickack_mode(sk);
+			tcp_enter_quickack_mode(sk, TCP_MAX_QUICKACKS);
 			inet_csk_reset_xmit_timer(sk, ICSK_TIME_DACK,
 						  TCP_DELACK_MAX, TCP_RTO_MAX);
 
@@ -5884,6 +5980,7 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb)
 	}
 	switch (sk->sk_state) {
 	case TCP_SYN_RECV:
+		tp->delivered++; /* SYN-ACK delivery isn't tracked in tcp_ack */
 		if (!tp->srtt_us)
 			tcp_synack_rtt_meas(sk, req);